{"id":"https://openalex.org/W4403210910","doi":"https://doi.org/10.1109/tc.2024.3475589","title":"Opara: Exploiting Operator Parallelism for Expediting DNN Inference on GPUs","display_name":"Opara: Exploiting Operator Parallelism for Expediting DNN Inference on GPUs","publication_year":2024,"publication_date":"2024-10-08","ids":{"openalex":"https://openalex.org/W4403210910","doi":"https://doi.org/10.1109/tc.2024.3475589"},"language":"en","primary_location":{"id":"doi:10.1109/tc.2024.3475589","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tc.2024.3475589","pdf_url":null,"source":{"id":"https://openalex.org/S157670870","display_name":"IEEE Transactions on Computers","issn_l":"0018-9340","issn":["0018-9340","0016-9340","1557-9956","2326-3814"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Computers","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5113076181","display_name":"Aodong Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I66867065","display_name":"East China Normal University","ror":"https://ror.org/02n96ep67","country_code":"CN","type":"education","lineage":["https://openalex.org/I66867065"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Aodong Chen","raw_affiliation_strings":["Shanghai Key Laboratory of Multidimensional Information Processing, School of Computer Science and Technology, East China Normal University, Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0006-8373-4465","affiliations":[{"raw_affiliation_string":"Shanghai Key Laboratory of Multidimensional Information Processing, School of Computer Science and Technology, East China Normal University, Shanghai, China","institution_ids":["https://openalex.org/I66867065"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029626585","display_name":"Fei Xu","orcid":"https://orcid.org/0000-0003-1590-5323"},"institutions":[{"id":"https://openalex.org/I66867065","display_name":"East China Normal University","ror":"https://ror.org/02n96ep67","country_code":"CN","type":"education","lineage":["https://openalex.org/I66867065"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fei Xu","raw_affiliation_strings":["Shanghai Key Laboratory of Multidimensional Information Processing, School of Computer Science and Technology, East China Normal University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0003-1590-5323","affiliations":[{"raw_affiliation_string":"Shanghai Key Laboratory of Multidimensional Information Processing, School of Computer Science and Technology, East China Normal University, Shanghai, China","institution_ids":["https://openalex.org/I66867065"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101566937","display_name":"Li Han","orcid":"https://orcid.org/0000-0001-5797-2554"},"institutions":[{"id":"https://openalex.org/I66867065","display_name":"East China Normal University","ror":"https://ror.org/02n96ep67","country_code":"CN","type":"education","lineage":["https://openalex.org/I66867065"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Li Han","raw_affiliation_strings":["School of Software Engineering, East China Normal University, Shanghai, China","School of Software Engineering, East China Normal University, Shangha, China"],"raw_orcid":"https://orcid.org/0000-0001-5797-2554","affiliations":[{"raw_affiliation_string":"School of Software Engineering, East China Normal University, Shanghai, China","institution_ids":["https://openalex.org/I66867065"]},{"raw_affiliation_string":"School of Software Engineering, East China Normal University, Shangha, China","institution_ids":["https://openalex.org/I66867065"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101145782","display_name":"Yuan Dong","orcid":null},"institutions":[{"id":"https://openalex.org/I66867065","display_name":"East China Normal University","ror":"https://ror.org/02n96ep67","country_code":"CN","type":"education","lineage":["https://openalex.org/I66867065"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuan Dong","raw_affiliation_strings":["Shanghai Key Laboratory of Multidimensional Information Processing, School of Computer Science and Technology, East China Normal University, Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0002-6571-5237","affiliations":[{"raw_affiliation_string":"Shanghai Key Laboratory of Multidimensional Information Processing, School of Computer Science and Technology, East China Normal University, Shanghai, China","institution_ids":["https://openalex.org/I66867065"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Li Chen","orcid":"https://orcid.org/0000-0002-2300-6996"},"institutions":[{"id":"https://openalex.org/I79516672","display_name":"University of Louisiana at Lafayette","ror":"https://ror.org/01x8rc503","country_code":"US","type":"education","lineage":["https://openalex.org/I2799628689","https://openalex.org/I79516672"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Li Chen","raw_affiliation_strings":["School of Computing and Informatics, University of Louisiana at Lafayette, Lafayette, LA, USA"],"raw_orcid":"https://orcid.org/0000-0002-2300-6996","affiliations":[{"raw_affiliation_string":"School of Computing and Informatics, University of Louisiana at Lafayette, Lafayette, LA, USA","institution_ids":["https://openalex.org/I79516672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100760218","display_name":"Zhi Zhou","orcid":"https://orcid.org/0000-0002-0987-9344"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhi Zhou","raw_affiliation_strings":["Guangdong Key Laboratory of Big Data Analysis and Processing, School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, China"],"raw_orcid":"https://orcid.org/0000-0002-0987-9344","affiliations":[{"raw_affiliation_string":"Guangdong Key Laboratory of Big Data Analysis and Processing, School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"last","author":{"id":null,"display_name":"Fangming Liu","orcid":"https://orcid.org/0000-0002-8570-1345"},"institutions":[{"id":"https://openalex.org/I4210136793","display_name":"Peng Cheng Laboratory","ror":"https://ror.org/03qdqbt06","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210136793"]},{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fangming Liu","raw_affiliation_strings":["Peng Cheng Laboratory, Shenzhen, China","Peng Cheng Laboratory, Huazhong University of Science and Technology, China"],"raw_orcid":"https://orcid.org/0000-0002-8570-1345","affiliations":[{"raw_affiliation_string":"Peng Cheng Laboratory, Shenzhen, China","institution_ids":["https://openalex.org/I4210136793"]},{"raw_affiliation_string":"Peng Cheng Laboratory, Huazhong University of Science and Technology, China","institution_ids":["https://openalex.org/I4210136793","https://openalex.org/I47720641"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.7071,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":{"value":0.84539793,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"74","issue":"1","first_page":"325","last_page":"333"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12702","display_name":"Brain Tumor Detection and Classification","score":0.9843999743461609,"subfield":{"id":"https://openalex.org/subfields/2808","display_name":"Neurology"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},"topics":[{"id":"https://openalex.org/T12702","display_name":"Brain Tumor Detection and Classification","score":0.9843999743461609,"subfield":{"id":"https://openalex.org/subfields/2808","display_name":"Neurology"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9828000068664551,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11775","display_name":"COVID-19 diagnosis using AI","score":0.958899974822998,"subfield":{"id":"https://openalex.org/subfields/2741","display_name":"Radiology, Nuclear Medicine and Imaging"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7714798450469971},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.7582526803016663},{"id":"https://openalex.org/keywords/expediting","display_name":"Expediting","score":0.7575527429580688},{"id":"https://openalex.org/keywords/parallelism","display_name":"Parallelism (grammar)","score":0.6836696863174438},{"id":"https://openalex.org/keywords/data-parallelism","display_name":"Data parallelism","score":0.6159098148345947},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.49360907077789307},{"id":"https://openalex.org/keywords/coprocessor","display_name":"Coprocessor","score":0.48115503787994385},{"id":"https://openalex.org/keywords/operator","display_name":"Operator (biology)","score":0.4476986825466156},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.42062678933143616},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.3816520571708679},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2124585211277008}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7714798450469971},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.7582526803016663},{"id":"https://openalex.org/C134448949","wikidata":"https://www.wikidata.org/wiki/Q1384274","display_name":"Expediting","level":2,"score":0.7575527429580688},{"id":"https://openalex.org/C2781172179","wikidata":"https://www.wikidata.org/wiki/Q853109","display_name":"Parallelism (grammar)","level":2,"score":0.6836696863174438},{"id":"https://openalex.org/C61483411","wikidata":"https://www.wikidata.org/wiki/Q3124522","display_name":"Data parallelism","level":3,"score":0.6159098148345947},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.49360907077789307},{"id":"https://openalex.org/C86111242","wikidata":"https://www.wikidata.org/wiki/Q859595","display_name":"Coprocessor","level":2,"score":0.48115503787994385},{"id":"https://openalex.org/C17020691","wikidata":"https://www.wikidata.org/wiki/Q139677","display_name":"Operator (biology)","level":5,"score":0.4476986825466156},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.42062678933143616},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.3816520571708679},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2124585211277008},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C86339819","wikidata":"https://www.wikidata.org/wiki/Q407384","display_name":"Transcription factor","level":3,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C158448853","wikidata":"https://www.wikidata.org/wiki/Q425218","display_name":"Repressor","level":4,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tc.2024.3475589","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tc.2024.3475589","pdf_url":null,"source":{"id":"https://openalex.org/S157670870","display_name":"IEEE Transactions on Computers","issn_l":"0018-9340","issn":["0018-9340","0016-9340","1557-9956","2326-3814"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Computers","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W2057392949","https://openalex.org/W2183341477","https://openalex.org/W2604662567","https://openalex.org/W2786171709","https://openalex.org/W2804032941","https://openalex.org/W2885579974","https://openalex.org/W2892341857","https://openalex.org/W3097411828","https://openalex.org/W3208777667","https://openalex.org/W4221109509","https://openalex.org/W4304192541","https://openalex.org/W4313229743","https://openalex.org/W4382202854","https://openalex.org/W4387321503","https://openalex.org/W4394922627","https://openalex.org/W4394944658","https://openalex.org/W4402896975","https://openalex.org/W6779728309","https://openalex.org/W6784999070","https://openalex.org/W6785377559","https://openalex.org/W6785429063","https://openalex.org/W7067822191"],"related_works":["https://openalex.org/W3145240193","https://openalex.org/W2147073383","https://openalex.org/W2540373069","https://openalex.org/W2950520577","https://openalex.org/W1554644772","https://openalex.org/W2003935582","https://openalex.org/W2494130044","https://openalex.org/W3170887803","https://openalex.org/W74409296","https://openalex.org/W3209384898"],"abstract_inverted_index":{"GPUs":[0],"have":[1],"become":[2],"the":[3,16,36,42,55,108,121,129,136,172,180],"<i>defacto</i>":[4],"hardware":[5],"devices":[6],"for":[7],"accelerating":[8],"Deep":[9],"Neural":[10],"Network":[11],"(DNN)":[12],"inference":[13,94],"workloads.":[14],"However,":[15],"conventional":[17],"<i>sequential":[18],"execution":[19,62,109,137],"mode":[20],"of":[21,45,52,110,124,138,150],"DNN":[22,86,93,117,164],"operators</i>":[23],"in":[24,60,155,177],"mainstream":[25],"deep":[26],"learning":[27],"frameworks":[28],"cannot":[29],"fully":[30],"utilize":[31],"GPU":[32,67],"resources,":[33],"even":[34],"with":[35,162,195],"operator":[37,57,130,182],"fusion":[38],"enabled,":[39],"due":[40],"to":[41,66,91,106,126,187],"increasing":[43],"complexity":[44],"model":[46],"structures":[47],"and":[48,70,84,103,140,145,165,179,190],"a":[49,82,148,156],"greater":[50],"diversity":[51],"operators.":[53,75,142],"Moreover,":[54],"<i>inadequate":[56],"launch":[58,131],"order</i>":[59],"parallelized":[61],"scenarios":[63],"can":[64],"lead":[65],"resource":[68,122],"wastage":[69],"unexpected":[71],"performance":[72],"interference":[73],"among":[74],"In":[76],"this":[77],"paper,":[78],"we":[79],"propose":[80],"<i>Opara</i>,":[81],"resource-":[83],"interference-aware":[85],"<u>Op</u>erator":[87],"<u>para</u>llel":[88],"scheduling":[89],"framework":[90],"accelerate":[92],"on":[95,133,153],"GPUs.":[96],"Specifically,":[97],"<i>Opara</i>":[98,119,151,170],"first":[99],"employs":[100],"<monospace>CUDA":[101,104,175],"Streams</monospace>":[102],"Graph</monospace>":[105,176],"<i>parallelize</i>":[107],"multiple":[111],"operators":[112,125],"automatically.":[113],"To":[114],"further":[115],"expedite":[116],"inference,":[118],"leverages":[120],"demands":[123],"judiciously":[127],"adjust":[128],"order":[132],"GPUs,":[134],"overlapping":[135],"compute-intensive":[139],"memory-intensive":[141],"We":[143],"implement":[144],"open":[146],"source":[147],"prototype":[149,160],"based":[152],"PyTorch":[154,178],"<i>non-intrusive</i>":[157],"manner.":[158],"Extensive":[159],"experiments":[161],"representative":[163],"Transformer-based":[166],"models":[167],"demonstrate":[168],"that":[169],"outperforms":[171],"default":[173],"sequential":[174],"state-of-the-art":[181],"parallelism":[183],"systems":[184],"by":[185],"up":[186],"<inline-formula><tex-math":[188,191],"notation=\"LaTeX\">$1.68\\boldsymbol{\\times}$</tex-math></inline-formula>":[189],"notation=\"LaTeX\">$1.29\\boldsymbol{\\times}$</tex-math></inline-formula>,":[192],"respectively,":[193],"yet":[194],"acceptable":[196],"runtime":[197],"overhead.":[198]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":1}],"updated_date":"2026-07-15T18:14:33.161393","created_date":"2024-10-09T00:00:00"}